Journal of Intensive Care最新文献

{"title":"Visualizing the dynamic mechanical power and time burden of mechanical ventilation patients: an analysis of the MIMIC-IV database.","authors":"Han Chen, Zhi-Zhong Chen, Shu-Rong Gong, Rong-Guo Yu","doi":"10.1186/s40560-023-00709-9","DOIUrl":"10.1186/s40560-023-00709-9","url":null,"abstract":"<p><strong>Background: </strong>Limiting driving pressure and mechanical power is associated with reduced mortality risk in both patients with and without acute respiratory distress syndrome. However, it is still poorly understood how the intensity of mechanical ventilation and its corresponding duration impact the risk of mortality.</p><p><strong>Methods: </strong>Critically ill patients who received mechanical ventilation were identified from the Medical Information Mart for Intensive Care (MIMIC)-IV database. A visualization method was developed by calculating the odds ratio of survival for all combinations of ventilation duration and intensity to assess the relationship between the intensity and duration of mechanical ventilation and the mortality risk.</p><p><strong>Results: </strong>A total of 6251 patients were included. The color-coded plot demonstrates the intuitive concept that episodes of higher dynamic mechanical power can only be tolerated for shorter durations. The three fitting contour lines represent 0%, 10%, and 20% increments in the mortality risk, respectively, and exhibit an exponential pattern: higher dynamic mechanical power is associated with an increased mortality risk with shorter exposure durations.</p><p><strong>Conclusions: </strong>Cumulative exposure to higher intensities and/or longer duration of mechanical ventilation is associated with worse outcomes. Considering both the intensity and duration of mechanical ventilation may help evaluate patient outcomes and guide adjustments in mechanical ventilation to minimize harmful exposure.</p>","PeriodicalId":16123,"journal":{"name":"Journal of Intensive Care","volume":null,"pages":null},"PeriodicalIF":7.1,"publicationDate":"2023-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10685677/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138460293","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Prognostic value of oxygen saturation index trajectory phenotypes on ICU mortality in mechanically ventilated patients: a multi-database retrospective cohort study.","authors":"Xiawei Shi, Yangyang Shi, Liming Fan, Jia Yang, Hao Chen, Kaiwen Ni, Junchao Yang","doi":"10.1186/s40560-023-00707-x","DOIUrl":"https://doi.org/10.1186/s40560-023-00707-x","url":null,"abstract":"<p><strong>Background: </strong>Heterogeneity among critically ill patients undergoing invasive mechanical ventilation (IMV) treatment could result in high mortality rates. Currently, there are no well-established indicators to help identify patients with a poor prognosis in advance, which limits physicians' ability to provide personalized treatment. This study aimed to investigate the association of oxygen saturation index (OSI) trajectory phenotypes with intensive care unit (ICU) mortality and ventilation-free days (VFDs) from a dynamic and longitudinal perspective.</p><p><strong>Methods: </strong>A group-based trajectory model was used to identify the OSI-trajectory phenotypes. Associations between the OSI-trajectory phenotypes and ICU mortality were analyzed using doubly robust analyses. Then, a predictive model was constructed to distinguish patients with poor prognosis phenotypes.</p><p><strong>Results: </strong>Four OSI-trajectory phenotypes were identified in 3378 patients: low-level stable, ascending, descending, and high-level stable. Patients with the high-level stable phenotype had the highest mortality and fewest VFDs. The doubly robust estimation, after adjusting for unbalanced covariates in a model using the XGBoost method for generating propensity scores, revealed that both high-level stable and ascending phenotypes were associated with higher mortality rates (odds ratio [OR]: 1.422, 95% confidence interval [CI] 1.246-1.623; OR: 1.097, 95% CI 1.027-1.172, respectively), while the descending phenotype showed similar ICU mortality rates to the low-level stable phenotype (odds ratio [OR] 0.986, 95% confidence interval [CI] 0.940-1.035). The predictive model could help identify patients with ascending or high-level stable phenotypes at an early stage (area under the curve [AUC] in the training dataset: 0.851 [0.827-0.875]; AUC in the validation dataset: 0.743 [0.709-0.777]).</p><p><strong>Conclusions: </strong>Dynamic OSI-trajectory phenotypes were closely related to the mortality of ICU patients requiring IMV treatment and might be a useful prognostic indicator in critically ill patients.</p>","PeriodicalId":16123,"journal":{"name":"Journal of Intensive Care","volume":null,"pages":null},"PeriodicalIF":7.1,"publicationDate":"2023-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10685672/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138460292","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Optimized ventilation power to avoid VILI.","authors":"Lauren T Thornton, John J Marini","doi":"10.1186/s40560-023-00706-y","DOIUrl":"10.1186/s40560-023-00706-y","url":null,"abstract":"<p><p>The effort to minimize VILI risk must be multi-pronged. The need to adequately ventilate, a key determinant of hazardous power, is reduced by judicious permissive hypercapnia, reduction of innate oxygen demand, and by prone body positioning that promotes both efficient pulmonary gas exchange and homogenous distributions of local stress. Modifiable ventilator-related determinants of lung protection include reductions of tidal volume, plateau pressure, driving pressure, PEEP, inspiratory flow amplitude and profile (using longer inspiration to expiration ratios), and ventilation frequency. Underappreciated conditional cofactors of importance to modulate the impact of local specific power may include lower vascular pressures and blood flows. Employed together, these measures modulate ventilation power with the intent to avoid VILI while achieving clinically acceptable targets for pulmonary gas exchange.</p>","PeriodicalId":16123,"journal":{"name":"Journal of Intensive Care","volume":null,"pages":null},"PeriodicalIF":7.1,"publicationDate":"2023-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10658809/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138176315","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The optimal dose of mobilisation therapy in the ICU: a prospective cohort study.","authors":"Marco Lorenz, Kristina Fuest, Bernhard Ulm, Julius J Grunow, Linus Warner, Annika Bald, Vanessa Arsene, Michael Verfuß, Nils Daum, Manfred Blobner, Stefan J Schaller","doi":"10.1186/s40560-023-00703-1","DOIUrl":"10.1186/s40560-023-00703-1","url":null,"abstract":"<p><strong>Background: </strong>This study aimed to assess the impact of duration of early mobilisation on survivors of critical illness. The hypothesis was that interventions lasting over 40 min, as per the German guideline, positively affect the functional status at ICU discharge.</p><p><strong>Methods: </strong>Prospective single-centre cohort study conducted in two ICUs in Germany. In 684 critically ill patients surviving an ICU stay > 24 h, out-of-bed mobilisation of more than 40 min was evaluated.</p><p><strong>Results: </strong>Daily mobilisation ≥ 40 min was identified as an independent predictor of an improved functional status upon ICU discharge. This effect on the primary outcome measure, change of Mobility-Barthel until ICU discharge, was observed in three different models for baseline patient characteristics (average treatment effect (ATE), all three models p < 0.001). When mobilisation parameters like level of mobilisation, were included in the analysis, the average treatment effect disappeared [ATE 1.0 (95% CI - 0.4 to 2.4), p = 0.16].</p><p><strong>Conclusions: </strong>A mobilisation duration of more than 40 min positively impacts functional outcomes at ICU discharge. However, the maximum level achieved during ICU stay was the most crucial factor regarding adequate dosage, as higher duration did not show an additional benefit in patients with already high mobilisation levels.</p><p><strong>Trial registration: </strong>Prospective Registry of Mobilization-, Routine- and Outcome Data of Intensive Care Patients (MOBDB), NCT03666286. Registered 11 September 2018-retrospectively registered, https://classic.</p><p><strong>Clinicaltrials: </strong>gov/ct2/show/NCT03666286 .</p>","PeriodicalId":16123,"journal":{"name":"Journal of Intensive Care","volume":null,"pages":null},"PeriodicalIF":7.1,"publicationDate":"2023-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10658796/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138176316","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Prolonged use of neuromuscular blocking agents is associated with increased long-term mortality in mechanically ventilated medical ICU patients: a retrospective cohort study.","authors":"Chun Lin, Wen-Cheng Chao, Kai-Chih Pai, Tsung-Ying Yang, Chieh-Liang Wu, Ming-Cheng Chan","doi":"10.1186/s40560-023-00696-x","DOIUrl":"10.1186/s40560-023-00696-x","url":null,"abstract":"<p><strong>Background: </strong>Neuromuscular blockade agents (NMBAs) can be used to facilitate mechanical ventilation in critically ill patients. Accumulating evidence has shown that NMBAs may be associated with intensive care unit (ICU)-acquired weakness and poor outcomes. However, the long-term impact of NMBAs on mortality is still unclear.</p><p><strong>Methods: </strong>We conducted a retrospective analysis using the 2015-2019 critical care databases at Taichung Veterans General Hospital, a referral center in central Taiwan, as well as the Taiwan nationwide death registry profile.</p><p><strong>Results: </strong>A total of 5709 ventilated patients were eligible for further analysis, with 63.8% of them were male. The mean age of enrolled subjects was 67.8 ± 15.8 years, and the one-year mortality was 48.3% (2755/5709). Compared with the survivors, the non-survivors had a higher age (70.4 ± 14.9 vs 65.4 ± 16.3, p < 0.001), Acute Physiology and Chronic Health Evaluation II score (28.0 ± 6.2 vs 24.7 ± 6.5, p < 0.001), a longer duration of ventilator use (12.6 ± 10.6 days vs 7.8 ± 8.5 days, p < 0.001), and were more likely to receive NMBAs for longer than 48 h (11.1% vs 7.8%, p < 0.001). After adjusting for age, sex, and relevant covariates, the use of NMBAs for longer than 48 h was found to be independently associated with an increased risk of mortality (adjusted HR: 1.261; 95% CI: 1.07-1.486). The analysis of effect modification revealed that this association was tended to be strong in patients with a Charlson Comorbidity Index of 3 or higher.</p><p><strong>Conclusions: </strong>Our study demonstrated that prolonged use of NMBAs was associated with an increased risk of long-term mortality in critically ill patients requiring mechanical ventilation. Further studies are needed to validate our findings.</p>","PeriodicalId":16123,"journal":{"name":"Journal of Intensive Care","volume":null,"pages":null},"PeriodicalIF":7.1,"publicationDate":"2023-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10655355/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136397770","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Variation in coagulation factor activity levels cause discrepancies between activated partial thromboplastin time and anti-Xa activity for heparin monitoring: a retrospective observational study.","authors":"Tomoyo Saito, Mineji Hayakawa, Osamu Kumano, Yoshinori Honma, Mone Murashita, Jun Kato, Syouki Fukui, Masaki Takahashi, Yuki Takahashi, Takumi Tsuchida, Asumi Mizugaki, Shuhei Takauji, Mariko Hayamizu, Tomonao Yoshida, Kenichi Katabami, Takeshi Wada, Kunihiko Maekawa","doi":"10.1186/s40560-023-00701-3","DOIUrl":"10.1186/s40560-023-00701-3","url":null,"abstract":"<p><strong>Background: </strong>Unfractionated heparin (UFH) is primarily monitored using activated partial thromboplastin time (APTT). However, the recent introduction of anti-activated factor X (anti-Xa) activity testing has provided a direct evaluation of Xa inhibition by anticoagulants. This study aimed to investigate discrepancies between APTT and anti-Xa activity during UFH monitoring in critically ill patients and explore their underlying causes.</p><p><strong>Methods: </strong>This study analyzed 271 pairs of laboratory test results from blood samples of 99 critically ill patients receiving continuous intravenous UFH. Theoretical APTT values were calculated using fitted curve equations from spiked sample measurements with anti-Xa activity. Samples were categorized into three groups based on the measurement of the APTT/theoretical APTT ratio: the lower group (< 80%), the concordant group (80-120%), and the upper group (> 120%).</p><p><strong>Results: </strong>The overall concordance rate between APTT and anti-Xa activity was 45%, with a 55% discrepancy rate. The lower group frequently showed apparent heparin overdoses, while coagulation factor activities in the lower and upper groups were higher and lower, respectively, than those in the concordant group. Particularly, the lower group exhibited higher factor VIII activity levels than the upper and concordant groups.</p><p><strong>Conclusions: </strong>Discrepancies between APTT and anti-Xa activity were frequently observed, influenced by changes in coagulation factors activity levels. The lower and upper groups were classified as pseudo-heparin-resistant and coagulopathy types, respectively. Accurate monitoring of heparin in critically ill patients is crucial, especially in cases of pseudo-heparin resistance, where APTT values may wrongly indicate inadequate heparin dosing despite sufficient anti-Xa activity. Understanding these discrepancies is important for managing heparin therapy in critically ill patients.</p><p><strong>Trial registration: </strong>Not applicable.</p>","PeriodicalId":16123,"journal":{"name":"Journal of Intensive Care","volume":null,"pages":null},"PeriodicalIF":7.1,"publicationDate":"2023-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10652491/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136397771","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Translation of patients' advance directives in intensive care units: are we there yet?","authors":"Sira M Baumann, Natalie J Kruse, Paulina S C Kliem, Simon A Amacher, Sabina Hunziker, Tolga D Dittrich, Fabienne Renetseder, Pascale Grzonka, Raoul Sutter","doi":"10.1186/s40560-023-00705-z","DOIUrl":"10.1186/s40560-023-00705-z","url":null,"abstract":"<p><strong>Objectives: </strong>This review examined studies regarding the implementation and translation of patients' advance directives (AD) in intensive care units (ICUs), focusing on practical difficulties and obstacles.</p><p><strong>Methods: </strong>The digital PubMed and Medline databases were screened using predefined keywords to identify relevant prospective and retrospective studies published until 2022.</p><p><strong>Results: </strong>Seventeen studies from the United States, Europe, and South Africa (including 149,413 patients and 1210 healthcare professionals) were identified. The highest prevalence of ADs was described in a prospective study in North America (49%), followed by Central Europe (13%), Asia (4%), Australia and New Zealand (4%), Latin America (3%), and Northern and Southern Europe (2.6%). While four retrospective studies reported limited effects of ADs, four retrospective studies, one survey and one systematic review indicated significant effects on provision of intensive care, higher rates of do-not-resuscitate orders, and care withholding in patients with ADs. Four of these studies showed shorter ICU stays, and lower treatment costs in patients with ADs. One prospective and two retrospective studies reported issues with loss, delayed or no transmission of ADs. One survey revealed that 91% of healthcare workers did not regularly check for ADs. Two retrospective studies and two survey revealed that the implementation of directives is further challenged by issues with their applicability, phrasing, and compliance by the critical care team and family members.</p><p><strong>Conclusions: </strong>Although ADs may improve intensive- and end-of-life care, insufficient knowledge, lack of awareness, poor communication between healthcare providers and patients or surrogates, lack of standardization of directives, as well as ethical and legal concerns challenge their implementation.</p>","PeriodicalId":16123,"journal":{"name":"Journal of Intensive Care","volume":null,"pages":null},"PeriodicalIF":7.1,"publicationDate":"2023-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10648602/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134649087","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Efficacy, safety, and pharmacokinetics of MR13A11A, a generic of remifentanil, for pain management of Japanese patients in the intensive care unit: a double-blinded, fentanyl-controlled, randomized, non-inferiority phase 3 study.","authors":"Matsuyuki Doi, Naoki Takahashi, Rumi Nojiri, Takehiko Hiraoka, Yusuke Kishimoto, Shinichi Inoue, Nobuyo Oya","doi":"10.1186/s40560-023-00698-9","DOIUrl":"10.1186/s40560-023-00698-9","url":null,"abstract":"<p><strong>Background: </strong>The aims of this study were to evaluate the efficacy, safety, and pharmacokinetics (PK) of continuous intravenous administration of remifentanil in mechanically ventilated patients in the intensive care unit (ICU).</p><p><strong>Methods: </strong>This was a multicenter, randomized, double-blinded, fentanyl-controlled, non-inferiority phase 3 study. Patients aged ≥ 20 years requiring 6 h to 10 days mechanical ventilation in an ICU and requiring pain relief were randomly assigned in a 1:1 ratio to receive either remifentanil (n = 98) or fentanyl (n = 98). Dose was titrated from an infusion rate of 1 mL/h (remifentanil: 0.025 µg/kg/min, fentanyl: 0.1 µg/kg/h) until the target level of analgesia (behavioral pain scale [BPS] ≤ 5 or numerical rating score [NRS] ≤ 3) was achieved by escalating the dose in 1 mL/h increasing. Administration was then adjusted to maintain the target level of analgesia until weaning from the ventilator. The primary endpoint was the proportion of patients who did not require rescue fentanyl. Safety was assessed according to standard procedures. PK of remifentanil in the arterial blood was assessed in 24 patients.</p><p><strong>Results: </strong>The proportion of patients achieving the primary endpoint in the remifentanil and fentanyl groups was 100% (92/92) and 97.8% (88/90), respectively. The difference between the groups was 2.2% (95% confidence interval, - 0.8-5.3) and non-inferiority of remifentanil to fentanyl was verified (p < 0.0001). The incidences of any adverse events in the remifentanil and fentanyl groups was 34 of 92 patients (37.0%) and 34 of 90 patients (37.8%), respectively. Adverse drug reactions was 12 in 92 patients (13.0%) and 15 in 90 patients (16.7%), respectively. In the PK analysis, blood remifentanil concentration decreased within 10 min to almost 50% of the end of administration, suggesting rapid offset of action following discontinuation of remifentanil.</p><p><strong>Conclusions: </strong>Remifentanil can be used safely for pain management in mechanically ventilated Japanese patients in the ICU.</p><p><strong>Trial registration: </strong>Japan Registry of Clinical Trials, jRCT2080224954. Registered 20 November 2019, https://jrct.niph.go.jp/latest-detail/jRCT2080224954 .</p>","PeriodicalId":16123,"journal":{"name":"Journal of Intensive Care","volume":null,"pages":null},"PeriodicalIF":7.1,"publicationDate":"2023-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10641973/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89718524","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Concerns with the revised Japanese recommendation for administering vitamin C to septic patients.","authors":"Harri Hemilä, Elizabeth Chalker","doi":"10.1186/s40560-023-00702-2","DOIUrl":"10.1186/s40560-023-00702-2","url":null,"abstract":"","PeriodicalId":16123,"journal":{"name":"Journal of Intensive Care","volume":null,"pages":null},"PeriodicalIF":7.1,"publicationDate":"2023-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10641959/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"92154745","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A deep learning model for predicting multidrug-resistant organism infection in critically ill patients.","authors":"Yaxi Wang, Gang Wang, Yuxiao Zhao, Cheng Wang, Chen Chen, Yaoyao Ding, Jing Lin, Jingjing You, Silong Gao, Xufeng Pang","doi":"10.1186/s40560-023-00695-y","DOIUrl":"10.1186/s40560-023-00695-y","url":null,"abstract":"<p><strong>Background: </strong>This study aimed to apply the backpropagation neural network (BPNN) to develop a model for predicting multidrug-resistant organism (MDRO) infection in critically ill patients.</p><p><strong>Methods: </strong>This study collected patient information admitted to the intensive care unit (ICU) of the Affiliated Hospital of Qingdao University from August 2021 to January 2022. All patients enrolled were divided randomly into a training set (80%) and a test set (20%). The least absolute shrinkage and selection operator and stepwise regression analysis were used to determine the independent risk factors for MDRO infection. A BPNN model was constructed based on these factors. Then, we externally validated this model in patients from May 2022 to July 2022 over the same center. The model performance was evaluated by the calibration curve, the area under the curve (AUC), sensitivity, specificity, and accuracy.</p><p><strong>Results: </strong>In the primary cohort, 688 patients were enrolled, including 109 (15.84%) MDRO infection patients. Risk factors for MDRO infection, as determined by the primary cohort, included length of hospitalization, length of ICU stay, long-term bed rest, antibiotics use before ICU, acute physiology and chronic health evaluation II, invasive operation before ICU, quantity of antibiotics, chronic lung disease, and hypoproteinemia. There were 238 patients in the validation set, including 31 (13.03%) MDRO infection patients. This BPNN model yielded good calibration. The AUC of the training set, the test set and the validation set were 0.889 (95% CI 0.852-0.925), 0.919 (95% CI 0.856-0.983), and 0.811 (95% CI 0.731-0.891), respectively.</p><p><strong>Conclusions: </strong>This study confirmed nine independent risk factors for MDRO infection. The BPNN model performed well and was potentially used to predict MDRO infection in ICU patients.</p>","PeriodicalId":16123,"journal":{"name":"Journal of Intensive Care","volume":null,"pages":null},"PeriodicalIF":7.1,"publicationDate":"2023-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10633993/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"71521680","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}